© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 74331
    Prev
    Next
    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ביניהם
    -0.07
     atenção
    -0.07
    克拉
    -0.07
     Bs
    -0.07
     acum
    -0.07
    Վ
    -0.07
     внимание
    -0.07
    猜
    -0.07
     coordination
    -0.07
    (var
    -0.07
    POSITIVE LOGITS
    켰
    0.08
    갓
    0.07
    烂
    0.07
    _weight
    0.07
    文学
    0.07
    てる
    0.07
    셨
    0.07
    题材
    0.07
    ילת
    0.07
     craz
    0.07
    Activations Density 0.006%

    No Known Activations